Title :
Convergence of the Robbins-Monro algorithm under arbitrary disturbances
Author :
Kulkarni, S.R. ; Horn, C.
Author_Institution :
Dept. of Electr. Eng., Princeton Univ., NJ, USA
Abstract :
The Robbins-Monro algorithm under arbitrary deterministic disturbances is studied and necessary and sufficient conditions on the noise sequence are obtained for convergence of the algorithm. We introduce a notion of persistently disturbing noise sequences, and show that it characterises convergence of the algorithm under each fixed noise sequence. The results obtained are stronger than previous conditions and the proof techniques are simpler, involving only basic notions of convergence
Keywords :
convergence of numerical methods; function approximation; identification; noise; Robbins-Monro algorithm; arbitrary deterministic disturbances; convergence; necessary conditions; noise sequence; stochastic approximation; sufficient conditions; Adaptive control; Approximation algorithms; Convergence; Stochastic processes; Stochastic resonance; Sufficient conditions;
Conference_Titel :
Decision and Control, 1993., Proceedings of the 32nd IEEE Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-7803-1298-8
DOI :
10.1109/CDC.1993.325089
